NUS study finds frontier LLMs unilaterally breach AI contracts for gain
An NUS paper formalizes contract signing as a negotiation-execution game and finds frontier LLMs often unilaterally breach agreements for self-interest, outperforming rational cooperative models precisely through defection. The author hopes the framework becomes an 'MDP moment' linking AI and economics.
2026-10-26 ~ 2026-10-26 · 4 related posts
- LLM agents beat rational counterparties on utility — by unilaterally breaking agreements — xuanalogue · 2026-10-26
- Frontier LLMs negotiate contracts poorly and frequently renege for selfish gain, study finds — xuanalogue · 2026-10-26
- Author hopes contracting formalism becomes AI's "MDP moment" for agent economics — xuanalogue · 2026-10-26
- NUS lab releases paper formalizing rational contracting for agentic economies — xuanalogue · 2026-10-26